init

api/endpoints.py

@@ -112,12 +112,49 @@ def reload_prompts(prompt_manager=Depends(get_prompt_manager)):
 @router.post("/api/ragflow/table-retrieval/reload")
 def reload_table_retrieval():
     syncer = RagflowSync()
-    result = syncer.sync_table_retrieval()
+    result = syncer.upload_table_retrieval()
     return {"ok": True, "result": result}
 
 
-@router.post("/api/ragflow/sql-gen/reload")
+@router.post("/api/ragflow/table-retrieval/upload")
-def reload_sql_gen():
+def upload_table_retrieval():
+    """上传表名检索模板文档"""
     syncer = RagflowSync()
-    result = syncer.sync_sql_gen_prompts()
+    try:
-    return {"ok": True, "result": result}
+        result = syncer.upload_table_retrieval()
+        return {"ok": True, "result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.put("/api/ragflow/table-retrieval/update")
+def update_table_retrieval(config: dict):
+    """更新表名检索知识库配置"""
+    syncer = RagflowSync()
+    try:
+        result = syncer.update_dataset(syncer._table_retrieval_dataset_id, config)
+        return {"ok": True, "result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.post("/api/ragflow/sql-gen/upload")
+def upload_sql_gen():
+    """上传 SQL 生成提示词文档"""
+    syncer = RagflowSync()
+    try:
+        result = syncer.upload_sql_gen()
+        return {"ok": True, "result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.put("/api/ragflow/sql-gen/update")
+def update_sql_gen(config: dict):
+    """更新 SQL 生成知识库配置"""
+    syncer = RagflowSync()
+    try:
+        result = syncer.update_dataset(syncer._sql_gen_dataset_id, config)
+        return {"ok": True, "result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

config/table_retrieval_prompts/tables.json

@@ -1,23 +1,24 @@
 {
-  "tables": {
+  "apbo_eta_ful": [
-    "apbo_eta_ful": [
+    "SO ETA INFO",
-      "SO ETA INFO",
+    "BO list",
-      "BO list",
+    "CC",
-      "CC",
+    "Commodity Code",
-      "Commodity Code",
+    "BO QTY",
-      "BO QTY",
+    "open order",
-      "open order",
+    "BO status",
-      "BO status",
+    "BO report",
-      "BO report",
+    "model",
-      "model",
+    "MTM SN",
-      "MTM SN",
+    "backlog",
-      "backlog",
+    "Premier",
-      "Premier",
+    "SN machine_sn",
-      "SN machine_sn",
+    "work order information",
-      "work order information",
+    "recovery ETA",
-      "recovery ETA",
+    "history order",
-      "history order",
+    "Warranty type"
-      "Warranty type"
+  ],
-    ]
+  "x_table_name": [
-  }
+    "xx"
-}
+  ]
+}

services/ragflow_sync.py

@@ -1,6 +1,6 @@
 import json
 import os
-from typing import Dict, List, Optional
+from typing import Any, Dict, List
 
 import httpx
 
@@ -8,25 +8,43 @@ from config import Config
 
 
 def _build_document_for_table(table: str, templates: List[str]) -> str:
-    lines = [f"table: {table}"]
+    """构建表名检索文档 - 使用更标准的格式"""
-    for t in templates:
+    lines = [
-        lines.append(f"- {t}")
+        f"# 表名检索模板: {table}",
+        "",
+        "## 可用模板:",
+        ""
+    ]
+    for i, t in enumerate(templates, 1):
+        lines.append(f"{i}. {t}")
+    lines.extend(["", f"表名: {table}", "类型: 表名检索模板"])
     return "\n".join(lines)
 
 
 def _build_sql_gen_document(table: str, prompt: Dict[str, any]) -> str:
+    """构建 SQL 生成文档 - 使用更标准的格式"""
     system_prompt = prompt.get("system_prompt", "")
     business_prompt = prompt.get("business_prompt", "")
     constraints = prompt.get("constraints", [])
-    lines = [f"table: {table}"]
+    
-    if system_prompt:
+    lines = [
-        lines.append("[system] " + system_prompt)
+        f"# SQL 生成提示词: {table}",
-    if business_prompt:
+        "",
-        lines.append("[business] " + business_prompt)
+        "## 系统提示词:",
+        system_prompt,
+        "",
+        "## 业务提示词:",
+        business_prompt,
+        ""
+    ]
+    
     if constraints:
-        lines.append("[constraints]")
+        lines.extend(["## 约束条件:", ""])
-        for c in constraints:
+        for i, c in enumerate(constraints, 1):
-            lines.append(f"- {c}")
+            lines.append(f"{i}. {c}")
+        lines.append("")
+    
+    lines.extend([f"表名: {table}", "类型: SQL 生成提示词"])
     return "\n".join(lines)
 
 
@@ -39,54 +57,187 @@ class RagflowSync:
         self._api_key = cfg.get("api_key", "")
         self._table_retrieval_dataset_id = (cfg.get("table_retrieval_dataset_id") or "").strip()
         self._sql_gen_dataset_id = (cfg.get("sql_gen_dataset_id") or "").strip()
-        self._upload_path = (cfg.get("upload") or "").strip()
-        self._upload_mode = (cfg.get("upload_mode") or "overwrite").strip().lower()
 
     def _validate_common(self) -> None:
         if not self._base_url:
             raise RuntimeError("未配置 ragflow.url")
         if not self._upload_path:
             raise RuntimeError("未配置 ragflow.upload 上传接口，请在 config/config.ini 中设置")
+        if "{dataset_id}" not in self._upload_path:
+            raise RuntimeError("上传接口路径必须包含 {dataset_id} 占位符")
         if self._upload_mode not in ("overwrite", "append"):
             raise RuntimeError("ragflow.upload_mode 仅支持 overwrite 或 append")
 
-    def _post(self, documents: List[Dict[str, any]]):
+    def _post(self, documents: List[Dict[str, Any]], dataset_id: str):
-        self._validate_common()
+        """上传文档到指定知识库 - 使用 multipart/form-data 格式"""
-        url = self._base_url + "/" + self._upload_path.lstrip("/")
+        if not self._base_url:
+            raise RuntimeError("未配置 ragflow.url")
+        
+        # 构建正确的 URL
+        upload_path = self._upload_path.replace("{dataset_id}", dataset_id)
+        url = self._base_url + "/" + upload_path.lstrip("/")
+        
         headers = {"Authorization": f"Bearer {self._api_key}"} if self._api_key else {}
-        payload: Dict[str, any] = {"documents": documents}
+        
-        if self._upload_mode == "overwrite":
+        # 由于接口使用 multipart/form-data，我们需要创建临时文件
-            payload["mode"] = "overwrite"
+        import tempfile
-        with httpx.Client(timeout=60) as client:
+        
-            response = client.post(url, json=payload, headers=headers)
+        # 创建临时文件并写入文档内容
-        response.raise_for_status()
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False, encoding='utf-8') as f:
-        return response.json()
+            # 将文档内容写入文件
+            for doc in documents:
+                content = doc.get('content', '')
+                f.write(content + '\n\n')
+            temp_file_path = f.name
+        
+        try:
+            # 使用 multipart/form-data 上传文件
+            files = {'file': open(temp_file_path, 'rb')}
+            
+            print(f"请求 URL: {url}")  # 调试信息
+            print(f"上传文件: {temp_file_path}")  # 调试信息
+                
+            with httpx.Client(timeout=60) as client:
+                response = client.post(url, files=files, headers=headers)
+            response.raise_for_status()
+            result = response.json()
+            print(f"RAGFlow 上传响应: {result}")  # 调试信息
+            return result
+        finally:
+            # 清理临时文件
+            import os
+            if os.path.exists(temp_file_path):
+                os.unlink(temp_file_path)
 
-    def sync_table_retrieval(self) -> Dict[str, any]:
+    def upload_documents(self, dataset_id: str, documents: List[Dict[str, Any]]) -> Dict[str, Any]:
+        """上传文档到指定知识库 - 使用 multipart/form-data 格式
+        
+        根据官方文档: POST /api/v1/datasets/{dataset_id}/documents
+        """
+        if not self._base_url:
+            raise RuntimeError("未配置 ragflow.url")
+        
+        # 构建正确的 URL
+        url = f"{self._base_url}/api/v1/datasets/{dataset_id}/documents"
+        
+        headers = {"Authorization": f"Bearer {self._api_key}"} if self._api_key else {}
+        
+        # 由于接口使用 multipart/form-data，我们需要创建临时文件
+        import tempfile
+        import os
+        
+        # 创建临时文件并写入文档内容
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False, encoding='utf-8') as f:
+            # 将文档内容写入文件
+            for doc in documents:
+                content = doc.get('content', '')
+                f.write(content + '\n\n')
+            temp_file_path = f.name
+        
+        try:
+            # 使用 multipart/form-data 上传文件
+            # 确保文件在 with 块内打开和关闭
+            with open(temp_file_path, 'rb') as file_obj:
+                files = {'file': file_obj}
+                
+                print(f"上传文档 URL: {url}")  # 调试信息
+                print(f"上传文件: {temp_file_path}")  # 调试信息
+                    
+                with httpx.Client(timeout=60) as client:
+                    response = client.post(url, files=files, headers=headers)
+                response.raise_for_status()
+                result = response.json()
+                print(f"RAGFlow 上传响应: {result}")  # 调试信息
+                
+                # 检查文档处理状态
+                if result.get('code') == 0 and result.get('data'):
+                    doc_id = result['data'][0].get('id')
+                    if doc_id:
+                        print(f"文档已上传，ID: {doc_id}")
+                        print("注意: 文档处理需要时间，请等待 RAGFlow 完成分块处理")
+                        print("可以在 RAGFlow 界面查看处理进度")
+                
+                return result
+        finally:
+            # 清理临时文件
+            if os.path.exists(temp_file_path):
+                try:
+                    os.unlink(temp_file_path)
+                except PermissionError:
+                    # 如果文件被占用，等待一下再重试
+                    import time
+                    time.sleep(0.1)
+                    try:
+                        os.unlink(temp_file_path)
+                    except PermissionError:
+                        print(f"警告: 无法删除临时文件 {temp_file_path}")
+
+    def update_dataset(self, dataset_id: str, config: Dict[str, Any]) -> Dict[str, Any]:
+        """更新知识库配置
+        
+        根据官方文档: PUT /api/v1/datasets/{dataset_id}
+        """
+        if not self._base_url:
+            raise RuntimeError("未配置 ragflow.url")
+        
+        url = f"{self._base_url}/api/v1/datasets/{dataset_id}"
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self._api_key}" if self._api_key else ""
+        }
+        
+        print(f"更新知识库 URL: {url}")  # 调试信息
+        print(f"更新配置: {config}")  # 调试信息
+        
+        with httpx.Client(timeout=60) as client:
+            response = client.put(url, json=config, headers=headers)
+        response.raise_for_status()
+        result = response.json()
+        print(f"RAGFlow 更新响应: {result}")  # 调试信息
+        return result
+
+    def upload_table_retrieval(self) -> Dict[str, Any]:
+        """上传表名检索模板文档 - 直接上传整个 JSON 文件"""
         if not self._table_retrieval_dataset_id:
-            raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法同步表名检索模板")
+            raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法上传表名检索模板")
+        
         root = os.path.dirname(os.path.dirname(__file__))
         tables_file = os.path.join(root, "config", "table_retrieval_prompts", "tables.json")
+        
+        if not os.path.exists(tables_file):
+            raise RuntimeError(f"表名检索模板文件不存在: {tables_file}")
+        
+        # 读取整个 JSON 文件内容
         with open(tables_file, "r", encoding="utf-8") as f:
             data = json.load(f)
+        
+        # 将 JSON 内容转换为字符串
+        json_content = json.dumps(data, ensure_ascii=False, indent=2)
+        
+        # 构建文档
+        doc = {
+            "content": f"# 表名检索模板库\n\n以下是所有表名检索模板的 JSON 数据：\n\n```json\n{json_content}\n```\n\n包含的表：{list(data.keys())}",
+            "metadata": {"type": "table_retrieval_templates", "format": "json"},
+            "title": "表名检索模板库",
+            "type": "table_template_library"
+        }
+        
+        print(f"生成的表名检索文档: {doc}")
+        
+        # 上传整个 JSON 文件内容
+        return self.upload_documents(self._table_retrieval_dataset_id, [doc])
 
-        tables = data.get("tables", {})
+    def upload_sql_gen(self) -> Dict[str, Any]:
-        documents = []
+        """上传 SQL 生成提示词文档"""
-        for table, templates in tables.items():
-            doc = {
-                "dataset_ids": self._table_retrieval_dataset_id,
-                "content": _build_document_for_table(table, templates),
-                "metadata": {"table": table},
-            }
-            documents.append(doc)
-
-        return self._post(documents)
-
-    def sync_sql_gen_prompts(self) -> Dict[str, any]:
         if not self._sql_gen_dataset_id:
-            raise RuntimeError("未配置 ragflow.sql_gen_dataset_id，无法同步 SQL 生成提示词")
+            raise RuntimeError("未配置 ragflow.sql_gen_dataset_id，无法上传 SQL 生成提示词")
+        
         root = os.path.dirname(os.path.dirname(__file__))
         prompts_dir = os.path.join(root, "config", "sql_gen_prompts")
+        
+        if not os.path.exists(prompts_dir):
+            raise RuntimeError(f"SQL 生成提示词目录不存在: {prompts_dir}")
+            
         documents = []
 
         for name in os.listdir(prompts_dir):
@@ -97,10 +248,12 @@ class RagflowSync:
                 prompt = json.load(f)
             table = prompt.get("table") or os.path.splitext(name)[0]
             doc = {
-                "dataset_ids": self._sql_gen_dataset_id,
                 "content": _build_sql_gen_document(table, prompt),
                 "metadata": {"table": table},
+                "title": f"SQL Prompt: {table}",
+                "type": "sql_prompt"
             }
             documents.append(doc)
+            print(f"生成的 SQL 提示词文档: {doc}")
 
-        return self._post(documents)
+        return self.upload_documents(self._sql_gen_dataset_id, documents)